Accelerated gradient descent method for functionals of probability measures by new convexity and smoothness based on transport maps

arXiv2305.05127MaRDI QIDQ6435855FDOQ6435855

Authors: Ken'ichiro Tanaka 

Publication date: 8 May 2023

Abstract: We consider problems of minimizing functionals $mathcalF$ of probability measures on the Euclidean space. To propose an accelerated gradient descent algorithm for such problems, we consider gradient flow of transport maps that give push-forward measures of an initial measure. Then we propose a deterministic accelerated algorithm by extending Nesterov's acceleration technique with momentum. This algorithm do not based on the Wasserstein geometry. Furthermore, to estimate the convergence rate of the accelerated algorithm, we introduce new convexity and smoothness for $mathcalF$ based on transport maps. As a result, we can show that the accelerated algorithm converges faster than a normal gradient descent algorithm. Numerical experiments support this theoretical result.

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Approximations to statistical distributions (nonasymptotic) (62E17) Numerical methods based on nonlinear programming (49M37)

This page was built for publication: Accelerated gradient descent method for functionals of probability measures by new convexity and smoothness based on transport maps

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6435855)